Adversarial Continual Learning for Multi-Domain Hippocampal Segmentation
This addresses the problem of training segmentation models under data restrictions for medical imaging applications, though it is incremental as it combines existing domain adaptation with continual learning.
The paper tackles catastrophic forgetting in continual learning for hippocampal segmentation in brain MRI by proposing an adversarial architecture that disentangles content from domain information using multiple datasets. The method reduces forgetting and outperforms state-of-the-art continual learning approaches.
Deep learning for medical imaging suffers from temporal and privacy-related restrictions on data availability. To still obtain viable models, continual learning aims to train in sequential order, as and when data is available. The main challenge that continual learning methods face is to prevent catastrophic forgetting, i.e., a decrease in performance on the data encountered earlier. This issue makes continuous training of segmentation models for medical applications extremely difficult. Yet, often, data from at least two different domains is available which we can exploit to train the model in a way that it disregards domain-specific information. We propose an architecture that leverages the simultaneous availability of two or more datasets to learn a disentanglement between the content and domain in an adversarial fashion. The domain-invariant content representation then lays the base for continual semantic segmentation. Our approach takes inspiration from domain adaptation and combines it with continual learning for hippocampal segmentation in brain MRI. We showcase that our method reduces catastrophic forgetting and outperforms state-of-the-art continual learning methods.